'MultiRNNCell' object is not iterable Python Tensorflow

Question

I am trying to add the weights and biases to tensorboard according to the layers. The following way I tried:

tf.reset_default_graph()

X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None,n_outputs])


layers = [tf.contrib.rnn.LSTMCell(num_units=n_neurons, 
                                 activation=tf.nn.leaky_relu, use_peepholes = True)
         for layer in range(n_layers)]
# for i, layer in enumerate(layers):
#     tf.summary.histogram('layer{0}'.format(i), tf.convert_to_tensor(layer))


multi_layer_cell = tf.contrib.rnn.MultiRNNCell(layers)
for index,one_lstm_cell in enumerate(multi_layer_cell):
    one_kernel, one_bias = one_lstm_cell.variables
    # I think TensorBoard handles summaries with the same name fine.
    tf.summary.histogram("Kernel", one_kernel)
    tf.summary.histogram("Bias", one_bias)
rnn_outputs, states = tf.nn.dynamic_rnn(multi_layer_cell, X, dtype=tf.float32)

stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, n_neurons]) 
stacked_outputs = tf.layers.dense(stacked_rnn_outputs, n_outputs)
outputs = tf.reshape(stacked_outputs, [-1, n_steps, n_outputs])
outputs = outputs[:,n_steps-1,:] # keep only last output of sequence

But I got the following error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-43-761df6e116a7> in <module>()
     44 
     45 multi_layer_cell = tf.contrib.rnn.MultiRNNCell(layers)
---> 46 for index,one_lstm_cell in enumerate(multi_layer_cell):
     47     one_kernel, one_bias = one_lstm_cell.variables
     48     # I think TensorBoard handles summaries with the same name fine.

TypeError: 'MultiRNNCell' object is not iterable

I would like to know what I have missed so that I can add the variables for visualization in the tensorboard. Kindly, help me.

Can someone please let me know what probably I am missing so that I can move forward? — Jaffer Wilson
– Jaffer Wilson, Commented Sep 5, 2018 at 10:52

javidcf · Accepted Answer · 2018-09-05 10:55:46Z

2

MultiRNNCell is indeed not iterable. For your case, first, the RNN variables will not be created until you call tf.nn.dynamic_rnn, so you should try to retrieve them after that. Second, with use_peephole you have more than kernel and bias variables. To retrieve them, you can access all the RNN variables together from multi_layer_cell.variables or each layer's own set through the cell objects stored in layers:

multi_layer_cell = tf.contrib.rnn.MultiRNNCell(layers)
rnn_outputs, states = tf.nn.dynamic_rnn(multi_layer_cell, X, dtype=tf.float32)
for index, one_lstm_cell in enumerate(layers):
    one_kernel, one_bias, *one_peepholes = one_lstm_cell.variables
    tf.summary.histogram("Kernel", one_kernel)
    tf.summary.histogram("Bias", one_bias)

answered Sep 5, 2018 at 10:55

javidcf

59.9k7 gold badges87 silver badges134 bronze badges

Sign up to request clarification or add additional context in comments.

12 Comments

Jaffer Wilson Over a year ago

How I can have the weights displayed on the Tensorboard and whether the output is layer wise or is there something else? Kindly, enlighten me sir.

javidcf Over a year ago

@JafferWilson Well that's another matter, it depends on what and how exactly you want to display. tf.summary.histogram will make a histogram out of all the values in the tensor and after a few plots you would get something like what is shown here.

Jaffer Wilson Over a year ago

ok I got it. Just one more query. I see there are three different weights, viz w_f_diag,w_i_diag andw_o_diag. Which of these weights should be considered for the visualization so that I can get a firm decision making, whether my model is going well or not?

Jaffer Wilson Over a year ago

Also, sir, I would like to know if I wanted to see whats going on in my LSTM model inside or behind the wall, is there anything I can get to see? Like a real time working , how the association are made within the model of my Multi cell RNN? Sir, kindly enlighten me, please.

javidcf Over a year ago

@JafferWilson Well in this case you have 5 weights per layer really, the kernel, the bias and the three you mention, which are for the "peepholes" (if you don't set use_peephole=True they will not appear). The naming for these I suppose follows the convention on Understanding LSTMs (see "Variants on Long Short Term Memory"). Here is a nice discussion on how to use histograms to figure out whether your training is working.

|

Collectives™ on Stack Overflow

'MultiRNNCell' object is not iterable Python Tensorflow

1 Answer 1

12 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

12 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related